Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
atsr
语帆96eaabca5b2e
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.pyindex bd8de3e87..87412bd87 100644--- a/funasr/utils/load_utils.py+++ b/funasr/utils/load_utils.py@@ -34,7 +34,6 @@ def load_audio_text_image_video(data_or_path_or_list, fs: int = 16000, audio_fs:if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local fileif data_type is None or data_type == "sound":data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list)- pdb.set_trace()if kwargs.get("reduce_channels", True):data_or_path_or_list = data_or_path_or_list.mean(0)elif data_type == "text" and tokenizer is not None: